DrewThomasson/ebook2audiobook

Generate audiobooks from e-books, voice cloning & 1158+ languages!

What it solves

It converts digital eBooks into high-quality audiobooks, allowing users to listen to their non-DRM books in a wide variety of languages and voices.

How it works

The tool processes eBook files (such as EPUB or PDF) and uses advanced Text-to-Speech (TTS) engines to synthesize speech. It supports multiple engines like XTTSv2, Bark, and VITS, and can perform voice cloning from a provided audio file. It also includes OCR scanning for image-based text pages and supports SML tags for fine-grained control over pauses and voice switching.

Who it’s for

Readers who want to turn their legal, non-DRM eBook collections into audiobooks, as well as developers or enthusiasts who want to use custom TTS models and voice cloning.

Highlights

  • Extensive Format Support: Converts from a wide range of formats including .epub, .pdf, .mobi, and .docx to various audio formats like .m4b, .mp3, and .wav.
  • Massive Language Support: Supports 1,158 languages and dialects.
  • Voice Cloning & Customization: Allows users to clone their own voices or use fine-tuned preset models.
  • Flexible Deployment: Can be run locally via a GUI (Gradio), in headless mode via CLI, or through Docker containers.
  • Low Resource Requirements: Minimum requirements of 2GB RAM and 1GB VRAM.
  • SML Tagging: Supports tags for adding specific breaks, pauses, and voice changes within the text.

Related

  • Project
    denizsafak/abogen

    A text-to-speech conversion tool that turns ePub, PDF, and text files into high-quality audio with synced subtitles using the Kokoro-82M model.

  • Project
    Xerophayze/TTS-Story

    TTS‑Story is a web UI for multi‑voice audiobook creation. It lets you tag speakers, design or clone voices (via Google Gemini Cloud or many local models), run a queue of TTS jobs, review audio in‑app, and export MP3/M4B. Supports 20+ engines, GPU/CPU isolation, bulk voice casting, directed‑narration, and optional LLM text‑prep.

  • Project
    Finrandojin/alexandria-audiobook

    Alexandria is a locally‑run web app that converts a text file (txt/md/epub) into a complete audiobook. It uses an LLM to annotate the book with speaker tags and TTS instructions, then synthesises each line with the built‑in Qwen‑3 TTS engine. Users can pick from nine preset voices, clone a voice from a short sample, fine‑tune voices with LoRA, or generate new voices from textual descriptions. The UI lets you edit the script, batch‑render audio (GPU‑accelerated), and export as MP3, M4B, or per‑speaker WAV tracks for Audacity.

  • Project
    KittenML/KittenTTS

    An open-source text-to-speech library featuring a 1.7B-parameter speech language model with in-context voice cloning and CPU-optimized inference.

  • Project
    estebanstifli/LocalText2Voice

    A free, open-source desktop app for long-form AI voice and video production, enabling the creation of audiobooks and documentaries using local or cloud TTS engines.